whn09 fdbb81f14f Neuron DSpark (#15): draft layers and main-cache writes as region graphs, decode rows padded to a power of two ... - DFlash forward_drafts per layer and update_main_cache (projection, then each layer's cache write) run as region graphs: eagerly the fp8 cast of the projection norm does not compile. - neuronx-cc rejects the sparse decode attention at 6 rows (a DSpark step with 5 drafts; ISA validation 'same_element_count_t2d'), 4 and 8 rows compile: multi-row decode steps pad to a power of two with empty rows. - bench_neuron.py --nextn: DSpark drafts, reports tokens per decode step. - Tiny checkpoint on device, cp=2, free-running greedy with drafts: nextn=3, 5, 7 all 9/9 golden tokens (short), nextn=5 long 9/9. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-24 13:41:17 +08:00
..
mtp	Neuron DSpark (#15): draft layers and main-cache writes as region graphs, decode rows padded to a power of two	2026-10-24 13:41:17 +08:00
v4_modules	Neuron MoE: two-level all-reduce (device, then across devices) (#27)	2026-10-24 11:05:25 +08:00
vision_encoder	initial commit	2026-10-20 12:09:42 +08:00
__init__.py	initial commit	2026-10-20 12:09:42 +08:00
decoder_layer.py	Neuron: optional whole-layer region graph (DEEPINFER_NEURON_REGION_LAYER)	2026-10-24 09:51:01 +08:00
deepseek_vl.py	Neuron: full DeepSeek-V4.1-Flash load + decode region graphs at EP=64 (issues #21, #25)	2026-10-23 01:39:22 +08:00
deepseek.py	Neuron: full DeepSeek-V4.1-Flash load + decode region graphs at EP=64 (issues #21, #25)	2026-10-23 01:39:22 +08:00